© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70827
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to demographics or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essian
    -0.07
    loh
    -0.06
    кан
    -0.06
    DUCT
    -0.06
     Jasper
    -0.06
    wick
    -0.06
    xC
    -0.06
     Bers
    -0.06
     Brady
    -0.06
    ame
    -0.06
    POSITIVE LOGITS
    SCO
    0.07
    λιο
    0.07
    -scrollbar
    0.06
    agna
    0.06
     there
    0.06
    ode
    0.06
    á»ĩn
    0.06
     اÙĨتشار
    0.06
     Carbon
    0.06
    aginator
    0.06
    Activations Density 0.002%

    No Known Activations